<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>音频伪造检测 on 语音/音频论文速递</title>
    <link>https://nanless.github.io/audio-paper-digest-blog/tags/%E9%9F%B3%E9%A2%91%E4%BC%AA%E9%80%A0%E6%A3%80%E6%B5%8B/</link>
    <description>Recent content in 音频伪造检测 on 语音/音频论文速递</description>
    <generator>Hugo</generator>
    <language>zh-cn</language>
    <lastBuildDate>Wed, 22 Apr 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://nanless.github.io/audio-paper-digest-blog/tags/%E9%9F%B3%E9%A2%91%E4%BC%AA%E9%80%A0%E6%A3%80%E6%B5%8B/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Audio Spoof Detection with GaborNet</title>
      <link>https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-22-audio-spoof-detection-with-gabornet/</link>
      <pubDate>Wed, 22 Apr 2026 00:00:00 +0000</pubDate>
      <guid>https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-22-audio-spoof-detection-with-gabornet/</guid>
      <description>本论文旨在解决传统SincNet前端在音频伪造检测中因有限长度sinc函数截断导致的频率泄漏问题。作者提出使用可学习的Gabor滤波器组（GaborNet）替代SincNet，并将其集成到两种先进的端到端检测架构RawNet2和RawGAT-ST中。同时，论文探索了将LEAF（Learnable F</description>
    </item>
  </channel>
</rss>
